Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2138 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.7037. Min Act: -0.0000

Data Index: 812799 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1260355 (The Pile)

Max Activating Token Index: 816

Text #2

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1605391 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1610636 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5748. Min Act: -0.0000

Data Index: 660532 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1670146 (The Pile)

Max Activating Token Index: 579

Text #6

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4901. Min Act: -0.0000

Data Index: 263449 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4828. Min Act: -0.0000

Data Index: 413126 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4535. Min Act: -0.0000

Data Index: 441394 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1898112 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1061505 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4086. Min Act: -0.0000

Data Index: 767842 (The Pile)

Max Activating Token Index: 806

Text #12

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4189. Min Act: -0.0000

Data Index: 195095 (The Pile)

Max Activating Token Index: 709

Text #13

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4317. Min Act: -0.0000

Data Index: 151046 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4074. Min Act: -0.0000

Data Index: 13578 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.3826. Min Act: -0.0000

Data Index: 639141 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1705716 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1681669 (The Pile)

Max Activating Token Index: 263

Text #18

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1682261 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.3670. Min Act: -0.0000

Data Index: 983840 (The Pile)

Max Activating Token Index: 444